Issue metadata
Sign in to add a comment
|
2.9% regression in runs/s clcokless_video_playback_vp9 media_perftests at 475343:475370 |
||||||||||||||||||||||
Issue descriptionThis is maybe noise. There was a slight bump from 26 -> 27 runs per second about 100 revisions before this "regression". The regression simply drops back down to the original runs/s. Filing a bug just in case we landed some improvement then immediately regressed it...
,
Jun 5 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8977595850996782512
,
Jun 5 2017
=== BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : thakis Commit : 5ea5799ced8c179ee57cf877d370e763e76d819c Date : Mon May 29 15:14:30 2017 Subject: Revert of Changing default Windows compiler to VS2017 (patchset #1 id:1 of https://codereview.chromium.org/2877993002/ ) Bisect Details Configuration: winx64_10_perf_bisect Benchmark : media_perftests Metric : clockless_video_playback_vp9/bear-vp9.webm Change : 2.93% | 26.9506118093 -> 26.1600496666 Revision Result N chromium@475342 26.9506 +- 0.120842 6 good chromium@475349 27.0164 +- 0.0447103 6 good chromium@475353 26.7315 +- 0.0825866 6 good chromium@475354 26.0754 +- 0.0914921 6 bad <-- chromium@475355 26.1346 +- 0.246382 6 bad chromium@475356 26.2101 +- 0.0993632 6 bad chromium@475370 26.16 +- 0.0884669 6 bad To Run This Test .\src\out\Release_x64\media_perftests.exe --single-process-tests Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8977595850996782512 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5814845439475712 | O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq | X | for more information addressing perf regression bugs. For feedback, | / \ | file a bug with component Speed>Bisection. Thank you! |
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by chcunningham@google.com
, Jun 5 2017